Diagnostics for linear L1 regression (also known as LAD - Least Absolute Deviations), including: estimation, confidence intervals, tests of hypotheses, measures of leverage, methods of diagnostics for L1 regression, special diagnostics graphs and measures of leverage. The algorithms are based in Dielman (2005) <doi:10.1080/0094965042000223680>, Elian et al. (2000) <doi:10.1080/03610920008832518> and Dodge (1997) <doi:10.1006/jmva.1997.1666>. This package builds on the quantreg package, which is a well-established package for tuning quantile regression models. There are also tests to verify if the errors have a Laplace distribution based on the work of Puig and Stephens (2000) <doi:10.2307/1270952>.

The social network literature features numerous methods for assigning value to paths as a function of their ties. gretel systemizes these approaches, casting them as instances of a generalized path value function indexed by a penalty parameter. The package also calculates probabilistic path value and identifies optimal paths in either value framework. Finally, proximity matrices can be generated in these frameworks that capture high-order connections overlooked in primitive adjacency sociomatrices. Novel methods are described in Buch (2019) <https://davidbuch.github.io/analyzing-networks-with-gretel.html>. More traditional methods are also implemented, as described in Yang, Knoke (2001) <doi:10.1016/S0378-8733(01)00043-0>.

Efficient algorithms for fitting the regularization path of linear regression, GLM, and Cox regression models with grouped penalties. This includes group selection methods such as group lasso, group MCP, and group SCAD as well as bi-level selection methods such as the group exponential lasso, the composite MCP, and the group bridge. For more information, see Breheny and Huang (2009) <doi:10.4310/sii.2009.v2.n3.a10>, Huang, Breheny, and Ma (2012) <doi:10.1214/12-sts392>, Breheny and Huang (2015) <doi:10.1007/s11222-013-9424-2>, and Breheny (2015) <doi:10.1111/biom.12300>, or visit the package homepage <https://pbreheny.github.io/grpreg/>.

The hybrid model likelihood as described by Ramos-Goñi et al. (2017) <doi:10.1097/MLR.0000000000000283> is implemented and and embedded in a latent class framework. The package is based on flexmix and among others contains an M-step-driver as described by Leisch (2004) <doi:10.18637/jss.v011.i08>. Users can, for example, estimate latent classes for EQ-5D value sets and address preference heterogeneity. Both uncensored and censored data are supported. Furthermore, heteroscedasticity can be taken into account. It is possible to control for different covariates on the continuous and dichotomous data and start values can differ between the expected latent classes.

This package implements the latent true-score and target-population anchored geometric standardized mean difference (LTG-SMD) framework for two-group effect-size analysis. Provides plug-in estimation, analytic delta-method confidence intervals using a sample fourth-moment plug-in, bias-corrected and bias-corrected-accelerated nonparametric bootstrap confidence intervals with study x group stratification, denominator-sensitivity profiles, and multi-site meta-analytic wrappers. Includes denominator-diagnostic reporting, a pluggable reliability estimator interface, and an explicit interface for specifying the target reference distribution. Companion software to Nakamura (2026) "The Denominator Chooses the Estimand: A Target-Population True-Score Framework for Standardized Mean Differences" <doi:10.1037/met0000875>.

N>=3 methods are used to measure each of n items. The data are used to estimate simultaneously systematic error (bias) and random error (imprecision). Observed measurements for each method or device are assumed to be linear functions of the unknown true values and the errors are assumed normally distributed. Pairwise calibration curves and plots can be easily generated. Unlike the ncb.od function, the omx function builds a one-factor measurement error model using OpenMx and allows missing values, uses full information maximum likelihood to estimate parameters, and provides both likelihood-based and bootstrapped confidence intervals for all parameters, in addition to Wald-type intervals.

Display processing results using the GWR (Geographically Weighted Regression) method, display maps, and show the results of the Mixed GWR (Mixed Geographically Weighted Regression) model which automatically selects global variables based on variability between regions. This function refers to Yasin, & Purhadi. (2012). "Mixed Geographically Weighted Regression Model (Case Study the Percentage of Poor Households in Mojokerto 2008)". European Journal of Scientific Research, 188-196. <https://www.researchgate.net/profile/Hasbi-Yasin-2/publication/289689583_Mixed_geographically_weighted_regression_model_case_study_The_percentage_of_poor_households_in_Mojokerto_2008/links/58e46aa40f7e9bbe9c94d641/Mixed-geographically-weighted-regression-model-case-study-The-percentage-of-poor-households-in-Mojokerto-2008.pdf>.

Compute bending energies, principal warps, partial warp scores, and the non-affine component of shape variation for 2D landmark configurations, as well as Mardia-Dryden distributions and self-similar distributions of landmarks, as described in Mitteroecker et al. (2020) <doi:10.1093/sysbio/syaa007>. Working examples to decompose shape variation into small-scale and large-scale components, and to decompose the total shape variation into outline and residual shape components are provided. Two landmark datasets are provided, that quantify skull morphology in humans and papionin primates, respectively from Mitteroecker et al. (2020) <doi:10.5061/dryad.j6q573n8s> and Grunstra et al. (2020) <doi:10.5061/dryad.zkh189373>.

This package provides functions to estimate the size-controlled phenotypic integration index, a novel method by Torices & Méndez (2014) <doi:10.1086/676622> to solve problems due to individual size when estimating integration (namely, larger individuals have larger components, which will drive a correlation between components only due to resource availability that might obscure the observed measures of integration). In addition, the package also provides the classical estimation by Wagner (1984) <doi:10.1007/BF00275224>, bootstrapping and jackknife methods to calculate confidence intervals and a significance test for both integration indices. Further details can be found in Torices & Muñoz-Pajares <doi:10.3732/apps.1400104>.

This package provides tools for designing and analyzing agricultural experiments. It includes functions for generating randomized treatment layouts for standard experimental designs such as Completely Randomized Design (CRD), Randomized Block Design (RBD), Latin Square Design (LSD), Factorial Randomized Block Design (FRBD), split-plot design, and strip-plot design. The package implements one-factor and two-factor analysis of variance (ANOVA) and offers multiple comparison procedures, including Least Significant Difference (lsd), Tukey, and Duncan tests, to compare treatment means in single-factor and factorial experiments. The methods follow classical experimental design principles described in Gomez and Gomez (1984, Statistical Procedures for Agricultural Research, John Wiley & Sons, New York).

In clinical trials, endpoints are sometimes evaluated with uncertainty. Adjudication is commonly adopted to ensure the study integrity. We propose to use multiple imputation (MI) introduced by Robin (1987) <doi:10.1002/9780470316696> to incorporate these uncertainties if reasonable event probabilities were provided. The method has been applied to Cox Proportional Hazard (PH) model, Kaplan-Meier (KM) estimation and Log-rank test in this package. Moreover, weighted estimations discussed in Cook (2004) <doi:10.1016/S0197-2456(00)00053-2> were also implemented with weights calculated from event probabilities. In conclusion, this package can handle time-to-event analysis if events presented with uncertainty by different methods.

cosmiq is a tool for the preprocessing of liquid- or gas - chromatography mass spectrometry (LCMS/GCMS) data with a focus on metabolomics or lipidomics applications. To improve the detection of low abundant signals, cosmiq generates master maps of the mZ/RT space from all acquired runs before a peak detection algorithm is applied. The result is a more robust identification and quantification of low-intensity MS signals compared to conventional approaches where peak picking is performed in each LCMS/GCMS file separately. The cosmiq package builds on the xcmsSet object structure and can be therefore integrated well with the package xcms as an alternative preprocessing step.

Computerized tomography (CT) can be used to assess certain wood properties when wood disks or logs are scanned. Wood density profiles (i.e. variations of wood density from pith to bark) can yield important information used for studies in forest resource assessment, wood quality and dendrochronology studies. The first step consists in transforming grey values from the scan images to density values. The packages then proposes a unique method to automatically locate the pith by combining an adapted Hough Transform method and a one-dimensional edge detector. Tree ring profiles (average ring density, earlywood and latewood density, ring width and percent latewood for each ring) are then obtained.

Functional clustering aims to group curves exhibiting similar temporal behaviour and to obtain representative curves summarising the typical dynamics within each cluster. A key challenge in this setting is class imbalance, where some clusters contain substantially more curves than others, which can adversely affect clustering performance. While class imbalance has been extensively studied in supervised classification, it has received comparatively little attention in unsupervised clustering. This package implements functional iterative hierarchical clustering ('funIHC'), an adaptation of the iterative hierarchical clustering method originally developed for multivariate data, to the functional data setting. For further details, please see Higgins and Carey (2024) <doi:10.1007/s11634-024-00611-8>.

Design and simulate fuzzy logic systems using Type-1 and Interval Type-2 Fuzzy Logic. This toolkit includes with graphical user interface (GUI) and an adaptive neuro- fuzzy inference system (ANFIS). This toolkit is a continuation from the previous package ('FuzzyToolkitUoN'). Produced by the Intelligent Modelling & Analysis Group (IMA) and Lab for UnCertainty In Data and decision making (LUCID), University of Nottingham. A big thank you to the many people who have contributed to the development/evaluation of the toolbox. Please cite the toolbox and the corresponding paper <doi:10.1109/FUZZ48607.2020.9177780> when using it. More related papers can be found in the NEWS.

This package provides convenient wrapper functions around the glue library for common string interpolation tasks. The package simplifies the process of combining glue string templating with common R functions like message(), warning(), stop(), print(), cat(), and file writing operations. Instead of manually calling glue() and then passing the result to these functions, glueDo provides direct wrapper functions that handle both steps in a single call. This is particularly useful for logging, error handling, and formatted output in R scripts and packages. The main reference for the underlying glue package is Hester and Bryan (2022) <https://CRAN.R-project.org/package=glue>.

Tabular data from statistical institutes and agencies are mostly confidential and must be protected prior to publications. The cell-key method is a post-tabular Statistical Disclosure Control perturbation technique that adds random noise to tabular data. The statistical properties of the perturbations are defined by some noise probability distributions - also referred to as perturbation tables. This tool can be used to create the perturbation tables based on a maximum entropy approach as described for example in Giessing (2016) <doi:10.1007/978-3-319-45381-1_18>. The perturbation tables created can finally be used to apply a cell-key method to frequency count or magnitude tables.

This package provides tools for both single and batch image manipulation and analysis (Olivoto, 2022 <doi:10.1111/2041-210X.13803>) and phytopathometry (Olivoto et al., 2022 <doi:10.1007/S40858-021-00487-5>). The tools can be used for the quantification of leaf area, object counting, extraction of image indexes, shape measurement, object landmark identification, and Elliptical Fourier Analysis of object outlines (Claude (2008) <doi:10.1007/978-0-387-77789-4>). The package also provides a comprehensive pipeline for generating shapefiles with complex layouts and supports high-throughput phenotyping of RGB, multispectral, and hyperspectral orthomosaics. This functionality facilitates field phenotyping using UAV- or satellite-based imagery.

This package implements the Bi-objective Lexicographical Classification method and Performance Assessment Ratio at 10% metric for algorithm classification. Constructs matrices representing algorithm performance under multiple criteria, facilitating decision-making in algorithm selection and evaluation. Analyzes and compares algorithm performance based on various metrics to identify the most suitable algorithms for specific tasks. This package includes methods for algorithm classification and evaluation, with examples provided in the documentation. Carvalho (2019) presents a statistical evaluation of algorithmic computational experimentation with infeasible solutions <doi:10.48550/arXiv.1902.00101>. Moreira and Carvalho (2023) analyze power in preprocessing methodologies for datasets with missing values <doi:10.1080/03610918.2023.2234683>.

This package provides functions implementing Single Source of Error state space models for purposes of time series analysis and forecasting. The package includes ADAM (Svetunkov, 2023, <https://openforecast.org/adam/>), Exponential Smoothing (Hyndman et al., 2008, <doi:10.1007/978-3-540-71918-2>), SARIMA (Svetunkov & Boylan, 2019 <doi: 10.1080/00207543.2019.1600764>), Complex Exponential Smoothing (Svetunkov & Kourentzes, 2018, <doi:10.13140/RG.2.2.24986.29123>), Simple Moving Average (Svetunkov & Petropoulos, 2018 <doi:10.1080/00207543.2017.1380326>) and several simulation functions. It also allows dealing with intermittent demand based on the iETS framework (Svetunkov & Boylan, 2019, <doi:10.13140/RG.2.2.35897.06242>).

This package provides a two-stage regression method that can be used when various input data types are correlated, for example gene expression and methylation in drug response prediction. In the first stage it uses the upstream features (such as methylation) to predict the response variable (such as drug response), and in the second stage it uses the downstream features (such as gene expression) to predict the residuals of the first stage. In our manuscript (Aben et al., 2016, <doi:10.1093/bioinformatics/btw449>), we show that using TANDEM prevents the model from being dominated by gene expression and that the features selected by TANDEM are more interpretable.

Interacts with a suite of web application programming interfaces (API) for taxonomic tasks, such as getting database specific taxonomic identifiers, verifying species names, getting taxonomic hierarchies, fetching downstream and upstream taxonomic names, getting taxonomic synonyms, converting scientific to common names and vice versa, and more. Some of the services supported include NCBI E-utilities (<https://www.ncbi.nlm.nih.gov/books/NBK25501/>), Encyclopedia of Life (<https://eol.org/docs/what-is-eol/data-services>), Global Biodiversity Information Facility (<https://techdocs.gbif.org/en/openapi/>), and many more. Links to the API documentation for other supported services are available in the documentation for their respective functions in this package.

Distributed Online Covariance Matrix Tests Docovt is a powerful tool designed to efficiently process and analyze distributed datasets. It enables users to perform covariance matrix tests in an online, distributed manner, making it highly suitable for large-scale data analysis. By leveraging advanced computational techniques, Docovt ensures robust and scalable solutions for statistical analysis, particularly in scenarios where data is dispersed across multiple nodes or sources. This package is ideal for researchers and practitioners working with high-dimensional data, providing a flexible and efficient framework for covariance matrix estimation and hypothesis testing. The philosophy of Docovt is described in Guo G.(2025) <doi:10.1016/j.physa.2024.130308>.

All datasets and functions required for the examples and exercises of the book "Data Science for Psychologists" (by Hansjoerg Neth, Konstanz University, 2026, <doi:10.5281/zenodo.7229812>), freely available at <https://hneth-ds4psy.share.connect.posit.cloud/>. The book and corresponding courses introduce principles and methods of data science to students of psychology and other biological or social sciences. The ds4psy package primarily provides datasets, but also functions for data generation and manipulation (e.g., of text and time data) and graphics that are used in the book and its exercises. All functions included in ds4psy are designed to be explicit and instructive, rather than efficient or elegant.